Traffic congestion prediction method and system based on job-residence trajectory

By obtaining and analyzing the historical signaling data of the on-board IoT card and user terminals, binding vehicles and users, determining the job-occupation trajectory, and predicting the traffic congestion probability, the problem of small granularity and insufficient accuracy of the existing traffic congestion prediction methods is solved. , achieving high accuracy prediction of traffic congestion in many days in the future.

CN115346359BActive Publication Date: 2024-11-08CHINA MOBILE (XIONGAN) ICT CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110518462.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-12
Publication Date
2024-11-08
Estimated Expiration
2041-05-12

AI Technical Summary

Technical Problem

The existing traffic congestion prediction methods have small granularity, and cannot make predictions in the world. The prediction accuracy and range are insufficient, and they cannot meet the needs of early planning of routes in certain scenarios.

Method used

By obtaining the historical signaling data of the on-board IoT card and user terminal, binding vehicles and users, determining the job-residential trajectory, obtaining historical traffic data of each section of the road based on the job-residential trajectory, and using a time series model to predict the probability of traffic congestion.

Benefits of technology

It has achieved high accuracy prediction of traffic congestion in many days in the future, with a large prediction granularity, meeting the needs of early planning of routes in certain scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115346359B_ABST
    Figure CN115346359B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for predicting traffic congestion based on work-residence trajectory, the method comprising: obtaining historical signaling data of vehicle-mounted Internet of Things cards and user terminals in a target area; binding each user terminal to a vehicle on which the vehicle-mounted Internet of Things card is installed according to the registration information of each vehicle-mounted Internet of Things card and the historical signaling data, and determining the work-residence trajectory of each user terminal according to the binding result; obtaining historical traffic flow data of each section of each time period every day according to the work-residence trajectory of each user terminal, so as to predict the probability of traffic congestion according to the historical traffic flow data. The present invention realizes the identification of multiple people in one vehicle by combining the signaling of the vehicle-mounted Internet of Things card and the mobile phone card, and predicts traffic congestion based on the work-residence trajectory, which can be used for prediction of multiple days in the future, and the prediction granularity is large, with high prediction accuracy.
Need to check novelty before this filing date? Find Prior Art